AnyLearning v0.1.41 - Context handling improvements

Llama.Assistant.RAG.Demo.-.1080p.mp4

🔧 Changes

• Utilize llama cpp KV cache mechanism to make faster inference. See (1)
• Summarize the chat history when it is about to exceeds the context length
• Recursive check and update missing setting from te DEFAULT CONFIG
• Add validators (type, min, max value) for input fields in the setting dialog

(1) llama cpp's KV cache check prefix of your chat history to reuse the K-V cache. For example:

• Generated sequence so far = "ABCDEF"
• If we modify the chat history somehow like: "ABCDXT". Then it matches prefix and reuses the cache for "ABCD" and newly computes the Key and Value vectors for "XT", then generates new responses.
  -> So we need to make the most of this mechanism by keep the history prefix as fixed as possible

AnyLearning v0.1.40 - RAG Support with LlamaIndex

🔧 Changes

• 💬 Supported continue conversation.
• 🔍 Added RAG support with LlamaIndex.
• ⚙️ Added model settings.
• 📝 Added markdown support.
• ⌛ Added loading text animation while downloading the models and generating answers.
• 🔄 Fixed chatbox scrolling issue.

Thank @gallegi for adding these features! 👍

Llama Assistant v0.1.32 - Build for macOS, Linux, Windows

🔧 Changes

• 🔄 Replace Whisper implementation with pywhispercpp.
• 🖥️ Add built versions:
  • 🍎 MacOS
  • 🪟 Windows
  • 🐧 Linux

Llama Assistant v0.1.28/29

🔧 Changes

• 🎙️🔥 Add offline STT support: WhisperCPP. The base model is downloaded from Hugging Face. Your audio is transcribed locally on your machine. 🔥

Llama Assistant v0.1.26

🔧 Changes

• Add binary build for MacOS with PyInstaller.

Llama Assistant v0.1.24

🐛 Bugfixes

• 🖱️ Fixed: wrong cursor position when inserting text.
• 💥 Fixed: crashing when changing shortcut.
• ⌨️ Fixed: wrong shortcut keys in macOS.
• 🙈 Hide "Copy Result" or "Clear" after clearing the chat.
• 🔄 Handle the last response correctly.

🔧 Changes

• 🧹 Clear results + input when clicking "Clear".
• ⌨️ Type "clear" or "cls" to clear.
• 🚫 Prevent action buttons when no data is input.

Llama Assistant v0.1.20

Features

• 📚 Text-only models: Llama 3.2 1B, 3B, Owen 2.5, and many more from HuggingFace.
• 🖼️ Multimodal models: LLaVA 1.5/1.6, MoonDream2, MiniCPM, and many more from HuggingFace.
• 🛠️ UI for adding custom models.
• ⚡ Streaming support for response!
• 🗣️ Wake word detection: "Hey Llama!".